Shapelearn Qwen 3.8 27B (13.1 GB VRAM)
syntaxing
34 points
2 comments
September 18, 2026
Related Discussions
Found 5 related stories in 136.3ms across 11,510 title embeddings via pgvector HNSW
- Qwen3.8-Max Bluestein · 25 pts · September 02, 2026 · 67% similar
- Qwen 3.8 27B erdaltoprak · 1016 pts · August 14, 2026 · 67% similar
- Qwen3.8 27B at 256K: 50 TPS on a 24 GB GPU pich · 37 pts · August 17, 2026 · 66% similar
- Qwen3.8 27B kristjansson · 12 pts · August 14, 2026 · 65% similar
- Qwen 3.8 27B on my laptop can interpret model weights, too theanonymousone · 552 pts · November 03, 2026 · 64% similar
Discussion Highlights (2 comments)
_ache_
From my own test. It's not faster than the unsloth model. Disclarer: I'm unsing Vulkan on an AMD GC.
sheo
Aged like milk https://news.ycombinator.com/item?id=49746618